Adapting Deep Network Features to Capture Psychological Representations

08/06/2016
by   Joshua C. Peterson, et al.
0

Deep neural networks have become increasingly successful at solving classic perception problems such as object recognition, semantic segmentation, and scene understanding, often reaching or surpassing human-level accuracy. This success is due in part to the ability of DNNs to learn useful representations of high-dimensional inputs, a problem that humans must also solve. We examine the relationship between the representations learned by these networks and human psychological representations recovered from similarity judgments. We find that deep features learned in service of object classification account for a significant amount of the variance in human similarity judgments for a set of animal images. However, these features do not capture some qualitative distinctions that are a key part of human representations. To remedy this, we develop a method for adapting deep features to align with human similarity judgments, resulting in image representations that can potentially be used to extend the scope of psychological experiments.

READ FULL TEXT

page 3

page 4

research
06/08/2017

Leveraging deep neural networks to capture psychological representations

Artificial neural networks have seen a recent surge in popularity for th...
research
03/05/2018

Totally Looks Like - How Humans Compare, Compared to Machines

Perceptual judgment of image similarity by humans relies on a rich inter...
research
05/29/2020

Extracting low-dimensional psychological representations from convolutional neural networks

Deep neural networks are increasingly being used in cognitive modeling a...
research
11/22/2020

Investigating Emotion-Color Association in Deep Neural Networks

It has been found that representations learned by Deep Neural Networks (...
research
10/13/2020

Transforming Neural Network Visual Representations to Predict Human Judgments of Similarity

Deep-learning vision models have shown intriguing similarities and diffe...
research
11/05/2017

Strategies for Conceptual Change in Convolutional Neural Networks

A remarkable feature of human beings is their capacity for creative beha...
research
07/17/2020

End-to-end Deep Prototype and Exemplar Models for Predicting Human Behavior

Traditional models of category learning in psychology focus on represent...

Please sign up or login with your details

Forgot password? Click here to reset